GenAI Cloud Engineer

Compensation: $65k – $100k • No equity

Position: GenAI Cloud Engineer Location: Newark, NJ Work Arrangement: Hybrid – 3 days onsite Duration: Long Term Contract

About the Opportunity

Our Client is seeking a GenAI Cloud Engineer to design, develop, and deploy enterprise-scale AI solutions that drive real business outcomes. This is a hands-on engineering role focused on building production-ready AI agents, agentic RAG applications, and cloud-native AI platforms that integrate with enterprise systems and support critical business workflows. The ideal candidate will have strong AWS cloud engineering experience combined with recent experience developing and deploying GenAI applications, AI agents, LLM-powered solutions, and modern microservices architectures.

Responsibilities

• Design, develop, and deploy cloud-native applications and AI-powered services using Python and JavaScript/TypeScript. • Build and support AI agents, agentic RAG solutions, multi-agent workflows, and conversational AI applications. • Develop microservices, APIs, event-driven workflows, and distributed applications within AWS environments. • Leverage Amazon Bedrock, Bedrock AgentCore, and related AI services to deliver production-grade AI solutions. • Implement retrieval pipelines, vector search, embeddings, semantic search, knowledge bases, and memory frameworks. • Integrate AI solutions with enterprise platforms, APIs, business systems, and data sources. • Develop orchestration workflows, tool routing, intent classification, guardrails, and human-in-the-loop controls. • Build observability, monitoring, tracing, evaluation, and quality assurance capabilities for AI applications. • Ensure security, governance, responsible AI practices, auditability, scalability, and operational reliability. • Collaborate closely with architects, data engineers, product teams, and business stakeholders to deliver enterprise AI initiatives. • Required Qualifications

• 5-7 years of software engineering experience developing cloud-native applications or AI/ML platforms. • Strong programming skills in Python and JavaScript/TypeScript. • Experience building APIs, microservices, asynchronous processing frameworks, and event-driven architectures. • Hands-on AWS experience including Lambda, IAM, EventBridge, container services, serverless technologies, and cloud-native deployment patterns. • Experience developing and deploying enterprise GenAI solutions, AI agents, agentic RAG applications, or LLM-powered platforms. • Experience with Amazon Bedrock, Bedrock AgentCore, or comparable LLM and agent platforms. • Experience with LangChain, LangGraph, MCP, A2A protocols, multi-agent frameworks, or workflow orchestration tools. • Strong understanding of prompt engineering, model evaluation, AI quality testing, feedback loops, and reliability measurement. • Experience with vector databases, embeddings, semantic retrieval, knowledge bases, and AI data pipelines. • Knowledge of AI governance, guardrails, security controls, access management, audit logging, and responsible AI practices. Preferred Qualifications • Experience working in regulated enterprise environments such as financial services, insurance, healthcare, or banking. • Experience leading technical workstreams and mentoring engineers. • Familiarity with enterprise integrations involving platforms such as Salesforce, Genesys, Service Platforms, and internal business applications. Technical Environment • Python • JavaScript / TypeScript • AWS Cloud Services • AWS Lambda • Amazon Bedrock • Bedrock AgentCore • FastAPI • LangChain • LangGraph • MCP • AI Agents • Agentic RAG • Vector Databases • EventBridge • Microservices Architecture • REST APIs • Distributed Systems • LLMs • Semantic Search • Embeddings.

Please let me know if you have any questions. I look forward to receiving your updated resume.